Comment by voidingw

I've used it for the following when I've had tokens to burn:

  - Fuzzing with the goal for it to apply domain-specific and source-informed knowledge to choose specific fuzzing approaches.
  - More generally, any optimization problem that benefits from domain-specific or source informed knowledge.
  - Running Microsoft's SkillOpt [0].

[0]: https://github.com/microsoft/SkillOpt